{"id":"https://openalex.org/W3135821167","doi":"https://doi.org/10.1145/3434074.3447189","title":"When Oracles Go Wrong: Using Preferences as a Means to Explore","display_name":"When Oracles Go Wrong: Using Preferences as a Means to Explore","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3135821167","doi":"https://doi.org/10.1145/3434074.3447189","mag":"3135821167"},"language":"en","primary_location":{"id":"doi:10.1145/3434074.3447189","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3447189","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3447189","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3447189","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070000164","display_name":"Isaac Sheidlower","orcid":"https://orcid.org/0009-0004-4487-8357"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac S. Sheidlower","raw_affiliation_strings":["Tufts University, Somerville, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Somerville, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Schaertl Short","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02748976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.8182107210159302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7657809257507324},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7159329652786255},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7080365419387817},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6622350215911865},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6453805565834045},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49798083305358887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46281707286834717},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.13165614008903503}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8182107210159302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657809257507324},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7159329652786255},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7080365419387817},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6622350215911865},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6453805565834045},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49798083305358887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46281707286834717},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.13165614008903503},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3434074.3447189","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3447189","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3447189","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3434074.3447189","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3434074.3447189","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3434074.3447189","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135821167.pdf","grobid_xml":"https://content.openalex.org/works/W3135821167.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W121023703","https://openalex.org/W1931877416","https://openalex.org/W1981276685","https://openalex.org/W1991618009","https://openalex.org/W1999874108","https://openalex.org/W2137375617","https://openalex.org/W2156869222","https://openalex.org/W2409653330","https://openalex.org/W2785324569","https://openalex.org/W2889659926","https://openalex.org/W2909713847","https://openalex.org/W2963106920","https://openalex.org/W3101754927","https://openalex.org/W3103105396","https://openalex.org/W3104248506","https://openalex.org/W4251846076","https://openalex.org/W4288083537","https://openalex.org/W4294326460"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4306904969","https://openalex.org/W2914522629","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"When":[0],"a":[1,7,11,33,73,97,103,122],"robot":[2],"is":[3],"deployed":[4],"to":[5,75,90,96,121],"learn":[6],"new":[8],"task":[9,35],"in":[10],"\"real-word\"":[12],"environment,":[13],"there":[14,26],"may":[15,27,38],"be":[16,28],"multiple":[17,21,29,65],"teachers":[18,37,66,109,113],"and":[19,36,67,93,110,114],"therefore":[20],"sources":[22],"of":[23,62],"feedback.":[24],"Furthermore,":[25],"optimal":[30],"solutions":[31],"for":[32,106],"given":[34],"have":[39],"preferences":[40],"among":[41],"those":[42],"various":[43],"solutions.":[44],"We":[45,79],"present":[46,102],"an":[47,87],"Interactive":[48],"Reinforcement":[49],"Learning":[50],"(I-RL)":[51],"algorithm,":[52],"Multi-Teacher":[53],"Activated":[54],"Policy":[55],"Shaping":[56],"(M-TAPS),":[57],"which":[58],"addresses":[59],"the":[60,77,91,115],"problem":[61],"learning":[63],"from":[64],"leverages":[68],"differences":[69],"between":[70],"them":[71],"as":[72],"means":[74],"explore":[76],"environment.":[78],"show":[80],"that":[81,117],"this":[82],"algorithm":[83],"can":[84],"significantly":[85],"increase":[86],"agent's":[88],"robustness":[89],"environment":[92],"quickly":[94],"adopt":[95],"teacher's":[98],"preferences.":[99],"Finally,":[100],"we":[101],"formal":[104],"model":[105],"comparing":[107],"human":[108],"constructed":[111],"oracle":[112],"way":[116],"they":[118],"provide":[119],"feedback":[120],"robot.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}